particleGPT
A GPT-style modeling pipeline for particle collision events: tokenization, training, sampling, untokenization, validation, metrics, and analysis.
A GPT-style modeling pipeline for particle collision events: tokenization, training, sampling, untokenization, validation, metrics, and analysis.
A technical design tool for reasoning about compute, data, model size, and expected loss from scaling-law papers.
Gameplay, networking, rendering-adjacent, and desktop tooling work built around performance, correctness, and iteration speed.
Backend systems using GameLift, RDS, DynamoDB, Cognito, Lambda, SNS, S3, and related infrastructure pieces.
Placeholder project for generative-model evaluation, detector-inspired plots, and comparison metrics for physics event data.
Placeholder project for experimenting with event-stream tokenization, starter prompts, sequence packing, and reversible data transforms.
Placeholder project for profiling notes, frame-time experiments, memory behavior, and low-latency systems engineering patterns.
Placeholder project for backend architecture, AWS infrastructure, experiment tracking, data movement, and research tooling systems.